International journal of disaster risk reduction最新文献_第8页

Holistic mapping of flood vulnerability in slums areas of Yaounde city, Cameroon through household and institutional surveys 通过家庭和机构调查对喀麦隆雅温得市贫民窟地区的洪水脆弱性进行整体测绘

IF 4.2 1区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

International journal of disaster risk reduction

Pub Date : 2024-11-01 DOI: 10.1016/j.ijdrr.2024.104947

Desmond N. Shiwomeh , Sameh A. Kantoush , Tetsuya Sumi , Binh Quang Nguyen , Karim I. Abdrabo

Urbanization in major cities has resulted in increasing urban slum expansion. This, together with increased climate-change-driven hazards, and deplorable slum characteristics has led to considerably higher flood impacts in slum settlements. As such, there is a need for specialized flood vulnerability assessment tools that integrate features specific to the urban slums. Studies have consecrated efforts to integrated and multidimensional flood vulnerability studies. However, assessments that include social, economic, structural, and institutional realities of the slum settlements are rare in developing countries. This study comprehensively assessed the flood vulnerability in urban slums. It offers a simplified perspective of vulnerability in urban slums, capturing data from slum inhabitants, local councils, experts, and local NGOs since they often have profound insights into essential service availability, access, and quality within the study area. Utilizing data encompassing 40 indicators (exposure, susceptibility, and resilience), we assess the physical/structural, social, and economic/psychological vulnerability indices for slum households and the institutional vulnerability of 41 entities. Despite significant challenges of poor infrastructure and lack of basic disaster management tools, slum residents have developed recognizable strategies to overcome flooding. Institutions carrying out intervention activities in the slums were largely incompetent and plagued with challenges ranging from lack of technical know-how to access to funds and coordination. Finally, a significant gap exists between state efforts and the impacts of these efforts on the residents of these slums. These findings complement household-level data and provide an expanded understanding of vulnerability patterns, thus informing policymakers about interventions.

大城市的城市化导致城市贫民窟日益扩大。这种情况，再加上气候变化导致的危害增加，以及贫民窟的恶劣特征，导致贫民窟住区受到的洪水影响大大增加。因此，需要有专门的洪水脆弱性评估工具，将城市贫民窟的具体特点纳入其中。各项研究都致力于综合、多维度的洪水脆弱性研究。然而，在发展中国家，将贫民窟的社会、经济、结构和制度现实纳入评估的情况并不多见。本研究全面评估了城市贫民窟的洪水脆弱性。由于贫民窟居民、地方议会、专家和地方非政府组织往往对研究区域内基本服务的可用性、获取途径和质量有着深刻的见解，因此本研究从简化的角度对城市贫民窟的脆弱性进行了评估，并从贫民窟居民、地方议会、专家和地方非政府组织那里获取了数据。利用包含 40 个指标（暴露、易受影响程度和复原力）的数据，我们对贫民窟家庭的物质/结构、社会和经济/心理脆弱性指数以及 41 个实体的机构脆弱性进行了评估。尽管面临基础设施薄弱、缺乏基本灾害管理工具等重大挑战，贫民窟居民仍制定了可识别的策略来克服洪灾。在贫民窟开展干预活动的机构大多能力不足，面临着从缺乏技术诀窍到获取资金和协调等各种挑战。最后，国家所做的努力与这些努力对贫民窟居民的影响之间存在巨大差距。这些研究结果补充了家庭层面的数据，扩大了对脆弱性模式的理解，从而为政策制定者提供了有关干预措施的信息。

{"title":"Holistic mapping of flood vulnerability in slums areas of Yaounde city, Cameroon through household and institutional surveys","authors":"Desmond N. Shiwomeh , Sameh A. Kantoush , Tetsuya Sumi , Binh Quang Nguyen , Karim I. Abdrabo","doi":"10.1016/j.ijdrr.2024.104947","DOIUrl":"10.1016/j.ijdrr.2024.104947","url":null,"abstract":"<div><div>Urbanization in major cities has resulted in increasing urban slum expansion. This, together with increased climate-change-driven hazards, and deplorable slum characteristics has led to considerably higher flood impacts in slum settlements. As such, there is a need for specialized flood vulnerability assessment tools that integrate features specific to the urban slums. Studies have consecrated efforts to integrated and multidimensional flood vulnerability studies. However, assessments that include social, economic, structural, and institutional realities of the slum settlements are rare in developing countries. This study comprehensively assessed the flood vulnerability in urban slums. It offers a simplified perspective of vulnerability in urban slums, capturing data from slum inhabitants, local councils, experts, and local NGOs since they often have profound insights into essential service availability, access, and quality within the study area. Utilizing data encompassing 40 indicators (exposure, susceptibility, and resilience), we assess the physical/structural, social, and economic/psychological vulnerability indices for slum households and the institutional vulnerability of 41 entities. Despite significant challenges of poor infrastructure and lack of basic disaster management tools, slum residents have developed recognizable strategies to overcome flooding. Institutions carrying out intervention activities in the slums were largely incompetent and plagued with challenges ranging from lack of technical know-how to access to funds and coordination. Finally, a significant gap exists between state efforts and the impacts of these efforts on the residents of these slums. These findings complement household-level data and provide an expanded understanding of vulnerability patterns, thus informing policymakers about interventions.</div></div>","PeriodicalId":13915,"journal":{"name":"International journal of disaster risk reduction","volume":"114 ","pages":"Article 104947"},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Assessing urban fire risk: An ensemble learning approach based on scenarios and cases 评估城市火灾风险：基于情景和案例的集合学习法

IF 4.2 1区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

International journal of disaster risk reduction

Pub Date : 2024-11-01 DOI: 10.1016/j.ijdrr.2024.104941

Shibo Cui, Ning Wang, Enhui Zhao, Jing Zhang, Chunli Zhang

Urban fires represent a significant hazard to people’s lives and property, which makes it critical to estimate the risk adequately. Existing urban fire evaluation methods lack applicability because they do not take into account individual scene components and previous cases. As a result, this study offers the scenario- and case-based urban fire risk assessment approach (SCBUFRA), which seeks to achieve a more thorough and accurate urban fire risk assessment. First, the technique uses fire case and scenario data, as well as the recursive feature elimination method, to pick the elements utilized to assess urban fire risk. Second, the data-driven empowerment technique and stability analysis are utilized to determine the precise fire risk value and correctly quantify the fire danger level in each part of the city. Next, the Affinity Propagation (AP) technique is used to cluster scene elements. Ensemble learning is then used to create a risk prediction model by refining the weighting strategy of

R^{2}

. Finally, Shapley additive explanations are used to investigate the elements causing urban fires. The findings show that SCBUFRA outperforms popular machine learning methods, that the number of crimes, gross population, and house price are the most important variables for fire prediction, and that the research is applicable to urban fire risk management and firefighting resource allocation.

城市火灾对人们的生命和财产构成重大威胁，因此充分估计风险至关重要。现有的城市火灾评估方法缺乏适用性，因为它们没有考虑到各个场景的组成部分和以往的案例。因此，本研究提出了基于场景和案例的城市火灾风险评估方法（SCBUFRA），旨在实现更全面、更准确的城市火灾风险评估。首先，该技术利用火灾案例和情景数据，以及递归特征消除法，挑选出用于评估城市火灾风险的要素。其次，利用数据驱动的授权技术和稳定性分析来确定精确的火灾风险值，并正确量化城市各区域的火灾危险等级。接着，使用亲和传播（AP）技术对场景元素进行聚类。然后，通过改进 R2 的加权策略，利用集合学习创建风险预测模型。最后，使用 Shapley 加法解释来研究导致城市火灾的因素。研究结果表明，SCBUFRA 优于流行的机器学习方法，犯罪数量、总人口和房价是火灾预测的最重要变量，该研究适用于城市火灾风险管理和消防资源分配。

{"title":"Assessing urban fire risk: An ensemble learning approach based on scenarios and cases","authors":"Shibo Cui, Ning Wang, Enhui Zhao, Jing Zhang, Chunli Zhang","doi":"10.1016/j.ijdrr.2024.104941","DOIUrl":"10.1016/j.ijdrr.2024.104941","url":null,"abstract":"<div><div>Urban fires represent a significant hazard to people’s lives and property, which makes it critical to estimate the risk adequately. Existing urban fire evaluation methods lack applicability because they do not take into account individual scene components and previous cases. As a result, this study offers the scenario- and case-based urban fire risk assessment approach (SCBUFRA), which seeks to achieve a more thorough and accurate urban fire risk assessment. First, the technique uses fire case and scenario data, as well as the recursive feature elimination method, to pick the elements utilized to assess urban fire risk. Second, the data-driven empowerment technique and stability analysis are utilized to determine the precise fire risk value and correctly quantify the fire danger level in each part of the city. Next, the Affinity Propagation (AP) technique is used to cluster scene elements. Ensemble learning is then used to create a risk prediction model by refining the weighting strategy of <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span>. Finally, Shapley additive explanations are used to investigate the elements causing urban fires. The findings show that SCBUFRA outperforms popular machine learning methods, that the number of crimes, gross population, and house price are the most important variables for fire prediction, and that the research is applicable to urban fire risk management and firefighting resource allocation.</div></div>","PeriodicalId":13915,"journal":{"name":"International journal of disaster risk reduction","volume":"114 ","pages":"Article 104941"},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Quantifying uncertainty in landslide susceptibility mapping due to sampling randomness 量化采样随机性导致的滑坡易发性绘图的不确定性

IF 4.2 1区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

International journal of disaster risk reduction

Pub Date : 2024-11-01 DOI: 10.1016/j.ijdrr.2024.104966

Lei-Lei Liu , Shuang-Lin Zhao , Can Yang , Wengang Zhang

The quality of landslide and non-landslide samples plays a crucial role in landslide susceptibility maps (LSMs) generated using machine learning algorithms. However, uncertainties arising from the collection of non-landslide samples can significantly compromise the reliability of these maps. Current methods, such as buffer-controlled sampling (BCS), often fail to address this issue adequately. This study aims to fill that gap by employing Monte Carlo simulations combined with BCS to quantify the uncertainties associated with non-landslide sampling and improve the accuracy of LSMs. A novel framework is proposed by incorporating landslide susceptibility confidence maps (LSCMs) to address the inherent uncertainty in BCS-based LSMs. The framework evaluates inconsistencies in LSMs, showing that maps generated by the same model may differ in over 30 % of the area due to variations in selection of non-landslide samples. The proposed approach outperforms traditional methods by correctly classifying landslide-prone areas, particularly in low and very low susceptibility zones, while providing a more reliable quantification of uncertainty. These findings underscore the limitations of traditional LSM methods and demonstrate that LSCMs offer a more robust tool for landslide hazard assessment. The framework enhances the precision of susceptibility mapping and provides critical insights for better risk mitigation and disaster preparedness.

滑坡和非滑坡样本的质量在使用机器学习算法生成的滑坡易感性图（LSM）中起着至关重要的作用。然而，收集非滑坡样本所产生的不确定性会严重影响这些地图的可靠性。缓冲控制采样 (BCS) 等现有方法往往无法充分解决这一问题。本研究旨在通过采用蒙特卡罗模拟结合 BCS 来量化与非滑坡取样相关的不确定性，并提高 LSM 的准确性，从而填补这一空白。通过结合滑坡易感性置信度图 (LSCM)，提出了一个新颖的框架，以解决基于 BCS 的 LSM 固有的不确定性。该框架对 LSM 中的不一致性进行了评估，结果表明，由于非滑坡样本选择的不同，同一模型生成的地图可能在 30% 以上的区域存在差异。所提出的方法优于传统方法，能正确划分滑坡易发区，尤其是在低易发区和极低易发区，同时还能提供更可靠的不确定性量化。这些发现强调了传统 LSM 方法的局限性，并证明 LSCM 为滑坡灾害评估提供了更强大的工具。该框架提高了易感性绘图的精确度，并为更好地减轻风险和备灾提供了重要见解。

{"title":"Quantifying uncertainty in landslide susceptibility mapping due to sampling randomness","authors":"Lei-Lei Liu , Shuang-Lin Zhao , Can Yang , Wengang Zhang","doi":"10.1016/j.ijdrr.2024.104966","DOIUrl":"10.1016/j.ijdrr.2024.104966","url":null,"abstract":"<div><div>The quality of landslide and non-landslide samples plays a crucial role in landslide susceptibility maps (LSMs) generated using machine learning algorithms. However, uncertainties arising from the collection of non-landslide samples can significantly compromise the reliability of these maps. Current methods, such as buffer-controlled sampling (BCS), often fail to address this issue adequately. This study aims to fill that gap by employing Monte Carlo simulations combined with BCS to quantify the uncertainties associated with non-landslide sampling and improve the accuracy of LSMs. A novel framework is proposed by incorporating landslide susceptibility confidence maps (LSCMs) to address the inherent uncertainty in BCS-based LSMs. The framework evaluates inconsistencies in LSMs, showing that maps generated by the same model may differ in over 30 % of the area due to variations in selection of non-landslide samples. The proposed approach outperforms traditional methods by correctly classifying landslide-prone areas, particularly in low and very low susceptibility zones, while providing a more reliable quantification of uncertainty. These findings underscore the limitations of traditional LSM methods and demonstrate that LSCMs offer a more robust tool for landslide hazard assessment. The framework enhances the precision of susceptibility mapping and provides critical insights for better risk mitigation and disaster preparedness.</div></div>","PeriodicalId":13915,"journal":{"name":"International journal of disaster risk reduction","volume":"114 ","pages":"Article 104966"},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel spatial-aware deep learning approach for exploring the environmental context of terrorist attacks and armed conflicts 探索恐怖袭击和武装冲突环境背景的新型空间感知深度学习方法

IF 4.2 1区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

International journal of disaster risk reduction

Pub Date : 2024-11-01 DOI: 10.1016/j.ijdrr.2024.104921

Zhan'ao Zhao , Kai Liu , Ming Wang

The quantitative assessment of terrorist attacks and armed conflicts (TAACs) is a crucial component of global public safety research and is vital for societal stability and national security. This study addresses the spatial dependency of such events, i.e., the relationship between the outbreak of an event and its environment. Based on geographic big data and artificial intelligence (AI), we propose a spatial feature utilization pattern that takes into account the impact of the event environment, and established a deep learning (DL) framework of features within the joint event location and space neighborhood to improve the precision of the quantitative assessment. The results demonstrate that in scenarios under a combination of 14 social, natural, and geographic driving factors, models that incorporate spatial features outperform those that only use location features during both the training and testing phases. Furthermore, models that consider both location and spatial features outperform models using only a single feature across various evaluation metrics. Global attribution analysis further confirms the spatial dependency of events, manifested in the mutual influence on the likelihood of events occurring among adjacent cities and the correlation with various environmental factors, particularly elements related to human activities and living environments. We find that both prosperous urban centers and underdeveloped rural areas are hotspots for TAACs, and that such events more likely to occur in harsh climatic patterns characterized by high temperatures and low precipitation. This enhances our understanding and preparedness for managing and preventing such events.

恐怖袭击和武装冲突（TAACs）的定量评估是全球公共安全研究的重要组成部分，对社会稳定和国家安全至关重要。本研究探讨了此类事件的空间依赖性，即事件爆发与环境之间的关系。基于地理大数据和人工智能（AI），我们提出了一种考虑到事件环境影响的空间特征利用模式，并在事件位置和空间邻域联合范围内建立了特征深度学习（DL）框架，以提高定量评估的精度。结果表明，在 14 种社会、自然和地理驱动因素共同作用下的场景中，包含空间特征的模型在训练和测试阶段的表现均优于仅使用位置特征的模型。此外，同时考虑位置和空间特征的模型在各种评价指标上都优于只使用单一特征的模型。全局归因分析进一步证实了事件的空间依赖性，表现为相邻城市间事件发生可能性的相互影响，以及与各种环境因素的相关性，尤其是与人类活动和生活环境相关的因素。我们发现，繁荣的城市中心和欠发达的农村地区都是 TAAC 的热点地区，而且这类事件更有可能发生在以高温和低降水为特征的恶劣气候模式中。这增强了我们对管理和预防此类事件的理解和准备。

{"title":"A novel spatial-aware deep learning approach for exploring the environmental context of terrorist attacks and armed conflicts","authors":"Zhan'ao Zhao , Kai Liu , Ming Wang","doi":"10.1016/j.ijdrr.2024.104921","DOIUrl":"10.1016/j.ijdrr.2024.104921","url":null,"abstract":"<div><div>The quantitative assessment of terrorist attacks and armed conflicts (TAACs) is a crucial component of global public safety research and is vital for societal stability and national security. This study addresses the spatial dependency of such events, i.e., the relationship between the outbreak of an event and its environment. Based on geographic big data and artificial intelligence (AI), we propose a spatial feature utilization pattern that takes into account the impact of the event environment, and established a deep learning (DL) framework of features within the joint event location and space neighborhood to improve the precision of the quantitative assessment. The results demonstrate that in scenarios under a combination of 14 social, natural, and geographic driving factors, models that incorporate spatial features outperform those that only use location features during both the training and testing phases. Furthermore, models that consider both location and spatial features outperform models using only a single feature across various evaluation metrics. Global attribution analysis further confirms the spatial dependency of events, manifested in the mutual influence on the likelihood of events occurring among adjacent cities and the correlation with various environmental factors, particularly elements related to human activities and living environments. We find that both prosperous urban centers and underdeveloped rural areas are hotspots for TAACs, and that such events more likely to occur in harsh climatic patterns characterized by high temperatures and low precipitation. This enhances our understanding and preparedness for managing and preventing such events.</div></div>","PeriodicalId":13915,"journal":{"name":"International journal of disaster risk reduction","volume":"114 ","pages":"Article 104921"},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Population activity recovery: Milestones unfolding, temporal interdependencies, and relationship with physical and social vulnerability 人口活动的恢复：正在展开的里程碑、时间上的相互依赖以及与身体和社会脆弱性的关系

IF 4.2 1区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

International journal of disaster risk reduction

Pub Date : 2024-11-01 DOI: 10.1016/j.ijdrr.2024.104931

Flavia-Ioana Patrascu , Ali Mostafavi

Understanding sequential community recovery milestones is crucial for proactive recovery planning and monitoring and targeted interventions. This study investigates these milestones related to population activities to examine their temporal interdependencies and evaluate the relationship between recovery milestones and physical (residential property damage) and socioeconomic vulnerability (through household income). This study leverages post-2017 Hurricane Harvey mobility data from Harris County to specify and analyze temporal recovery milestones and their interdependencies. The analysis examined four key milestones: return to evacuated areas, recovery of essential and non-essential services, and the rate of home-switch (moving out of residences). Robust linear regression validates interdependencies between across milestone lags and sequences: achieving earlier milestones accelerates subsequent recovery milestones. The study thus identifies six primary recovery milestone sequences. We found that socioeconomic vulnerability accounted through the median household income level, rather than physical vulnerability to flooding accounted through the property damage extent, correlates with recovery delays between milestones. We studied variations in recovery sequences across lower and upper quantiles of property damage extent and median household income: lower property damage extent and lower household income show greater representation in the “slowest to recover” sequence, while households with greater damage and higher income are predominant in the group with the “fastest recovery sequences”. Milestone sequence variability aligns closely with income, independent of physical vulnerability. This empowers emergency managers to effectively monitor and manage recovery efforts, enabling timely interventions.

了解连续的社区恢复里程碑对于积极的恢复规划、监测和有针对性的干预措施至关重要。本研究调查了这些与人口活动相关的里程碑，以研究其时间上的相互依赖性，并评估恢复里程碑与物理（住宅财产损失）和社会经济脆弱性（通过家庭收入）之间的关系。本研究利用哈里斯县 2017 年 "哈维 "飓风后的流动性数据，明确并分析了时间上的恢复里程碑及其相互依存关系。分析考察了四个关键的里程碑：返回疏散地区、基本和非基本服务的恢复以及家庭转换率（搬离住所）。稳健的线性回归验证了各里程碑滞后期和序列之间的相互依存关系：实现早期里程碑可加快后续恢复里程碑的实现。因此，本研究确定了六个主要的恢复里程碑序列。我们发现，通过家庭收入中位数计算的社会经济脆弱性，而不是通过财产损失程度计算的洪灾物理脆弱性，与里程碑之间的恢复延迟相关。我们研究了财产损失程度和家庭收入中位数的上下限恢复顺序的变化：财产损失程度较低和家庭收入较低的家庭在 "恢复最慢 "的顺序中占有较大比例，而财产损失程度较高和收入较高的家庭在 "恢复最快 "的顺序中占有较大比例。里程碑序列的变化与收入密切相关，与身体脆弱性无关。这使应急管理人员能够有效地监测和管理恢复工作，及时采取干预措施。

{"title":"Population activity recovery: Milestones unfolding, temporal interdependencies, and relationship with physical and social vulnerability","authors":"Flavia-Ioana Patrascu , Ali Mostafavi","doi":"10.1016/j.ijdrr.2024.104931","DOIUrl":"10.1016/j.ijdrr.2024.104931","url":null,"abstract":"<div><div>Understanding sequential community recovery milestones is crucial for proactive recovery planning and monitoring and targeted interventions. This study investigates these milestones related to population activities to examine their temporal interdependencies and evaluate the relationship between recovery milestones and physical (residential property damage) and socioeconomic vulnerability (through household income). This study leverages post-2017 Hurricane Harvey mobility data from Harris County to specify and analyze temporal recovery milestones and their interdependencies. The analysis examined four key milestones: return to evacuated areas, recovery of essential and non-essential services, and the rate of home-switch (moving out of residences). Robust linear regression validates interdependencies between across milestone lags and sequences: achieving earlier milestones accelerates subsequent recovery milestones. The study thus identifies six primary recovery milestone sequences. We found that socioeconomic vulnerability accounted through the median household income level, rather than physical vulnerability to flooding accounted through the property damage extent, correlates with recovery delays between milestones. We studied variations in recovery sequences across lower and upper quantiles of property damage extent and median household income: lower property damage extent and lower household income show greater representation in the “slowest to recover” sequence, while households with greater damage and higher income are predominant in the group with the “fastest recovery sequences”. Milestone sequence variability aligns closely with income, independent of physical vulnerability. This empowers emergency managers to effectively monitor and manage recovery efforts, enabling timely interventions.</div></div>","PeriodicalId":13915,"journal":{"name":"International journal of disaster risk reduction","volume":"114 ","pages":"Article 104931"},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Spatial analysis of major industrial risks of petroleum origin in urban areas - The case of the city of Hassi-Messaoud 城市地区源自石油的主要工业风险的空间分析 - 哈西-梅萨乌德市的案例

IF 4.2 1区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

International journal of disaster risk reduction

Pub Date : 2024-11-01 DOI: 10.1016/j.ijdrr.2024.104916

Lahcene Bouzouaid , Kamal Youcef

Aiming at an efficient management of its oil sector and ensuring safety for its population and property, Algeria is currently engaged in all-out assessment approach. Efficient management and safety prove to be crucial parameters in oil-related activity. The major risks degree of the severity of whatever nature have impacts of various and diverse dimensions. The current study presents an occasional paradox case that which combines all high-risk elements and specific factors associated with them in an urban environment, which is made fragile and vulnerable due to its heavy exposure to a highly probable danger. The city of Hassi-Messaoud, the most important component of the Country's economy, witnesses an alarming spatial development driven by an exceptional population growth. The latter is primarily expressed through the incessant influx of immigrants attracted by promising job prospects in the oil industry sector. Coupled with the uncontrolled population movement, the urban expansion lends itself to the most dramatic aspect of Hassi-Messaoud and eventually exposes it to certain dangers all the more as Hassi-Messaoud is located in an area subject to significant potential oil-based risks.

为了有效地管理其石油部门并确保其人口和财产的安全，阿尔及利亚目前正在进行全面评估。事实证明，高效管理和安全是石油相关活动的关键参数。重大风险的严重程度无论性质如何，都会产生各种不同的影响。目前的研究提出了一个偶然的矛盾案例，即在一个城市环境中结合了所有高风险因素和与之相关的特定因素，而这个城市环境由于极有可能面临危险而变得脆弱不堪。Hassi-Messaoud 市是该国经济最重要的组成部分，在人口超常增长的推动下，该市的空间发展令人震惊。人口增长的主要表现形式是被石油工业的良好就业前景所吸引的移民的不断涌入。由于人口流动不受控制，城市扩张成为 Hassi-Messaoud 最引人注目的一面，并最终使其面临更多的危险，因为 Hassi-Messaoud 位于一个存在重大潜在石油风险的地区。

{"title":"Spatial analysis of major industrial risks of petroleum origin in urban areas - The case of the city of Hassi-Messaoud","authors":"Lahcene Bouzouaid , Kamal Youcef","doi":"10.1016/j.ijdrr.2024.104916","DOIUrl":"10.1016/j.ijdrr.2024.104916","url":null,"abstract":"<div><div>Aiming at an efficient management of its oil sector and ensuring safety for its population and property, Algeria is currently engaged in all-out assessment approach. Efficient management and safety prove to be crucial parameters in oil-related activity. The major risks degree of the severity of whatever nature have impacts of various and diverse dimensions. The current study presents an occasional paradox case that which combines all high-risk elements and specific factors associated with them in an urban environment, which is made fragile and vulnerable due to its heavy exposure to a highly probable danger. The city of Hassi-Messaoud, the most important component of the Country's economy, witnesses an alarming spatial development driven by an exceptional population growth. The latter is primarily expressed through the incessant influx of immigrants attracted by promising job prospects in the oil industry sector. Coupled with the uncontrolled population movement, the urban expansion lends itself to the most dramatic aspect of Hassi-Messaoud and eventually exposes it to certain dangers all the more as Hassi-Messaoud is located in an area subject to significant potential oil-based risks.</div></div>","PeriodicalId":13915,"journal":{"name":"International journal of disaster risk reduction","volume":"114 ","pages":"Article 104916"},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Quantifying post-disaster community well-being: A case study of Hurricane Harvey 量化灾后社区福祉：哈维飓风案例研究

IF 4.2 1区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

International journal of disaster risk reduction

Pub Date : 2024-11-01 DOI: 10.1016/j.ijdrr.2024.104903

Mohamadali Morshedi , Makarand Hastak , Satish V. Ukkusuri , Seungyoon Lee

Natural hazards such as hurricanes affect various aspects of the community members’ lives and their post-disaster well-being by causing significant disruptions in the key community activities in the immediate recovery phase. Furthermore, natural hazards leave behind short-term socio-economic impacts such as stress, anxiety, huge recovery expense, and lack of affordable housing. There is a need for incorporating both immediate and short-term impacts of natural hazards when measuring disaster recovery. This study aims to address this need by introducing community well-being as the metric for the recovery of communities from natural disasters. From this perspective, community resilience is defined as the capability of community to reach its pre-disaster state of well-being, in a timely and efficient manner. The study leverages Bottom-Up Spillover Theory and the existing literature to introduce a community well-being model. This model quantifies how the functionality of infrastructure systems can affect various aspects of community well-being based on 6 domains, 17 sub-domains, and 51 indicators. The indicators were quantified using survey data and 211-call data for the City of Houston, and data on the impact of Hurricane Harvey at the zip code level. The results showed that various dimensions of well-being were affected heterogeneously and followed different recovery patterns. The proposed framework can serve decision makers as a dashboard for identifying the well-being domains and sub-domains that should be addressed to enhance post-disaster well-being in the immediate-to short-term. Furthermore, the study introduces the phone call data as an inexpensive and timely replacement for multiple rounds of survey questionnaires for quantifying community well-being.

飓风等自然灾害会影响社区成员生活的各个方面以及他们的灾后福祉，在直接恢复阶段会严重扰乱社区的主要活动。此外，自然灾害还会带来短期的社会经济影响，如压力、焦虑、巨额恢复费用和缺乏负担得起的住房。在衡量灾后恢复情况时，有必要将自然灾害的直接影响和短期影响都考虑在内。本研究旨在满足这一需求，将社区福祉作为衡量社区从自然灾害中恢复的标准。从这一角度出发，社区恢复力被定义为社区及时有效地达到灾前福祉状态的能力。本研究利用自下而上的溢出理论和现有文献，引入了社区福祉模型。该模型基于 6 个领域、17 个子领域和 51 个指标，量化了基础设施系统的功能如何影响社区福祉的各个方面。这些指标是利用休斯顿市的调查数据和 211 呼叫数据，以及飓风哈维在邮政编码层面的影响数据进行量化的。结果显示，福祉的各个维度受到不同程度的影响，并遵循不同的恢复模式。所提出的框架可作为决策者的仪表板，用于确定应在近期至短期内解决的福祉领域和子领域，以提高灾后福祉。此外，该研究还介绍了电话数据，它可以廉价、及时地取代多轮调查问卷，用于量化社区福祉。

{"title":"Quantifying post-disaster community well-being: A case study of Hurricane Harvey","authors":"Mohamadali Morshedi , Makarand Hastak , Satish V. Ukkusuri , Seungyoon Lee","doi":"10.1016/j.ijdrr.2024.104903","DOIUrl":"10.1016/j.ijdrr.2024.104903","url":null,"abstract":"<div><div>Natural hazards such as hurricanes affect various aspects of the community members’ lives and their post-disaster well-being by causing significant disruptions in the key community activities in the immediate recovery phase. Furthermore, natural hazards leave behind short-term socio-economic impacts such as stress, anxiety, huge recovery expense, and lack of affordable housing. There is a need for incorporating both immediate and short-term impacts of natural hazards when measuring disaster recovery. This study aims to address this need by introducing community well-being as the metric for the recovery of communities from natural disasters. From this perspective, community resilience is defined as the capability of community to reach its pre-disaster state of well-being, in a timely and efficient manner. The study leverages Bottom-Up Spillover Theory and the existing literature to introduce a community well-being model. This model quantifies how the functionality of infrastructure systems can affect various aspects of community well-being based on 6 domains, 17 sub-domains, and 51 indicators. The indicators were quantified using survey data and 211-call data for the City of Houston, and data on the impact of Hurricane Harvey at the zip code level. The results showed that various dimensions of well-being were affected heterogeneously and followed different recovery patterns. The proposed framework can serve decision makers as a dashboard for identifying the well-being domains and sub-domains that should be addressed to enhance post-disaster well-being in the immediate-to short-term. Furthermore, the study introduces the phone call data as an inexpensive and timely replacement for multiple rounds of survey questionnaires for quantifying community well-being.</div></div>","PeriodicalId":13915,"journal":{"name":"International journal of disaster risk reduction","volume":"114 ","pages":"Article 104903"},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Disaster awareness levels and institutional responsibility perceptions of international students in Turkey 土耳其留学生对灾害的认识水平和对机构责任的看法

IF 4.2 1区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

International journal of disaster risk reduction

Pub Date : 2024-11-01 DOI: 10.1016/j.ijdrr.2024.104939

Salih Ciftci, Leyla Ciftci

This study aimed to investigate the disaster awareness levels and institutional responsibility perceptions of international students in Turkey. Turkey is a country that is prone to natural disasters, and it is important to receive disaster training to be prepared for disasters. Turkey hosts more than three hundred thousand international students from 198 different countries. Bartın is one of the cities where international students receive education. Bartın is a risky city in terms of disasters such as earthquakes, floods, and landslides. This is why it is highly important for international students living in Bartın to receive disaster training. Other important issues include which institutions they would reach in a disaster situation, how they would reach them, and how they should act during a disaster. It was determined that 40 % of the participants had not received disaster training and were not sufficiently knowledgeable about relevant institutions. It was also observed that some of the responses of the participants were influenced by their gender, age, duration of living in Turkey, whether there was a risk of disasters in their home country, disaster experiences, whether they experienced loss in disasters, and whether they had received disaster-related training.

本研究旨在调查土耳其留学生的灾害意识水平和机构责任感。土耳其是一个自然灾害频发的国家，接受防灾培训以做好防灾准备非常重要。土耳其接纳了来自198个不同国家的30多万名留学生。巴特恩是留学生接受教育的城市之一。就地震、洪水和山体滑坡等灾害而言，巴特恩是一个风险较高的城市。因此，对居住在巴特恩的留学生来说，接受防灾培训非常重要。其他重要问题还包括：在发生灾害时，他们会联系哪些机构，如何联系这些机构，以及在发生灾害时应如何行动。结果发现，40% 的参与者没有接受过灾害培训，对相关机构的了解也不够。调查还发现，参与者的某些回答受其性别、年龄、在土耳其的居住时间、本国是否存在灾害风险、灾害经历、是否在灾害中遭受过损失以及是否接受过与灾害有关的培训等因素的影响。

{"title":"Disaster awareness levels and institutional responsibility perceptions of international students in Turkey","authors":"Salih Ciftci, Leyla Ciftci","doi":"10.1016/j.ijdrr.2024.104939","DOIUrl":"10.1016/j.ijdrr.2024.104939","url":null,"abstract":"<div><div>This study aimed to investigate the disaster awareness levels and institutional responsibility perceptions of international students in Turkey. Turkey is a country that is prone to natural disasters, and it is important to receive disaster training to be prepared for disasters. Turkey hosts more than three hundred thousand international students from 198 different countries. Bartın is one of the cities where international students receive education. Bartın is a risky city in terms of disasters such as earthquakes, floods, and landslides. This is why it is highly important for international students living in Bartın to receive disaster training. Other important issues include which institutions they would reach in a disaster situation, how they would reach them, and how they should act during a disaster. It was determined that 40 % of the participants had not received disaster training and were not sufficiently knowledgeable about relevant institutions. It was also observed that some of the responses of the participants were influenced by their gender, age, duration of living in Turkey, whether there was a risk of disasters in their home country, disaster experiences, whether they experienced loss in disasters, and whether they had received disaster-related training.</div></div>","PeriodicalId":13915,"journal":{"name":"International journal of disaster risk reduction","volume":"114 ","pages":"Article 104939"},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142586189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

How have regional evacuation conditions changed over time? Evacuation model for alternative scenarios given the accident environment, regional environment, and social systems 地区疏散条件随着时间的推移发生了怎样的变化？在事故环境、区域环境和社会系统的条件下，建立可供选择的疏散模型

IF 4.2 1区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

International journal of disaster risk reduction

Pub Date : 2024-11-01 DOI: 10.1016/j.ijdrr.2024.104959

Weihua Zhang , Wenmei Gai , Wuyi Cheng , Liaoying Zhou

The rapid evacuation in major leak accidents during hazardous chemical transportation is critical for protecting people in risk areas. An approach integrating the accident environment, regional environment, and social system is proposed to perform evacuation evaluation in such accidents. An agent-based modeling framework consisting of warning mechanisms, evacuation preparation process, as well as evacuation modes and movement process, is developed to comprehensively model the evacuation process. The regional environmental and social system data from 1964 to 2020 of Jiangsu Province in China is applied to analyze whether the changes in evacuation conditions have correspondingly affected evacuation effectiveness. A regional evacuation model simulating a real liquid chlorine leak accident during transportation in Wuzhong of Jiangsu Province is constructed to test the effectiveness and applicability of the proposed method. It is found that a 9 % change in the diffusion rate of warning messages triggered by environmental cues with the evolution of the study area settlements following the chronological changes; while the evolution of media technology allows for the rapid diffusion of warning messages and the rapid loading of a large number of individuals into the regional evacuation network; Years with faster warning diffusion have not been the most efficient ones in terms of overall evacuation; The distribution of buildings and population substantially impacts the overall evacuation effectiveness, while the former has a more significant impact. The study results can provide information for public emergency authorities to develop effective early warning resource allocation and evacuation organization plans.

在危险化学品运输过程中发生重大泄漏事故时，快速疏散对于保护风险区域内的人员至关重要。本文提出了一种整合事故环境、区域环境和社会系统的方法来进行此类事故的疏散评估。建立了一个基于代理的建模框架，包括预警机制、疏散准备过程以及疏散模式和移动过程，以全面模拟疏散过程。应用中国江苏省 1964 年至 2020 年的区域环境和社会系统数据，分析疏散条件的变化是否相应地影响了疏散效果。建立了一个模拟江苏省吴中区运输过程中液氯泄漏事故的区域疏散模型，以检验所提出方法的有效性和适用性。研究发现，随着研究区域居民点的演变，环境线索触发的预警信息扩散率随时间变化而变化，变化率为 9%；而媒体技术的发展使预警信息得以快速扩散，大量个体快速加载到区域疏散网络中；从整体疏散效果来看，预警扩散较快的年份并不是效率最高的年份；建筑物和人口的分布对整体疏散效果有很大影响，而前者的影响更为显著。研究结果可为公共应急部门制定有效的预警资源分配和疏散组织方案提供信息。

{"title":"How have regional evacuation conditions changed over time? Evacuation model for alternative scenarios given the accident environment, regional environment, and social systems","authors":"Weihua Zhang , Wenmei Gai , Wuyi Cheng , Liaoying Zhou","doi":"10.1016/j.ijdrr.2024.104959","DOIUrl":"10.1016/j.ijdrr.2024.104959","url":null,"abstract":"<div><div>The rapid evacuation in major leak accidents during hazardous chemical transportation is critical for protecting people in risk areas. An approach integrating the accident environment, regional environment, and social system is proposed to perform evacuation evaluation in such accidents. An agent-based modeling framework consisting of warning mechanisms, evacuation preparation process, as well as evacuation modes and movement process, is developed to comprehensively model the evacuation process. The regional environmental and social system data from 1964 to 2020 of Jiangsu Province in China is applied to analyze whether the changes in evacuation conditions have correspondingly affected evacuation effectiveness. A regional evacuation model simulating a real liquid chlorine leak accident during transportation in Wuzhong of Jiangsu Province is constructed to test the effectiveness and applicability of the proposed method. It is found that a 9 % change in the diffusion rate of warning messages triggered by environmental cues with the evolution of the study area settlements following the chronological changes; while the evolution of media technology allows for the rapid diffusion of warning messages and the rapid loading of a large number of individuals into the regional evacuation network; Years with faster warning diffusion have not been the most efficient ones in terms of overall evacuation; The distribution of buildings and population substantially impacts the overall evacuation effectiveness, while the former has a more significant impact. The study results can provide information for public emergency authorities to develop effective early warning resource allocation and evacuation organization plans.</div></div>","PeriodicalId":13915,"journal":{"name":"International journal of disaster risk reduction","volume":"114 ","pages":"Article 104959"},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FloodDamageCast: Building flood damage nowcasting with machine-learning and data augmentation FloodDamageCast：利用机器学习和数据增强技术建立洪水灾害预报系统

IF 4.2 1区地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY

International journal of disaster risk reduction

Pub Date : 2024-11-01 DOI: 10.1016/j.ijdrr.2024.104971

Chia-Fu Liu , Lipai Huang , Kai Yin , Sam Brody , Ali Mostafavi

Near-real-time estimation of damages (a.k.a, damage nowcasting) to building and infrastructure is crucial during response and recovery efforts. Despite advancements in flood risk predictions, the majority of existing methods primarily focus on inundation estimation with limited damage nowcasting capabilities. Flooding damage nowcasting at fine spatial resolutions remains a very challenging problem with currently no existing model to perform the task. This limitation is mainly due to a number of technical challenges such as limited consideration of non-linear interactions between flood hazards and build-environment features, issues with imbalanced datasets, and the absence of reliable ground truth for model performance evaluation. To address this important gap, this study presents FloodDamageCast, a machine learning (ML) framework tailored for property flood damage nowcasting. The framework leverages heterogeneous data related to the built environment, topographic, and hydrological features to predict residential flood damage in a fine resolution of 500 m by 500 m in the context of Harris County, TX, during the 2017 Hurricane Harvey. To deal with data imbalance, FloodDamageCast includes a tabular data augmentation model based on Conditional Tabular Generative Adversarial Networks (CTGAN). The data augmentation model component addresses highly imbalanced class issues, where the majority class constitutes 96.4% of the dataset, potentially impairing model performance, By combining GAN-based data augmentation with an efficient ML model, Light Gradient-Boosting Machine (LightGBM), our results demonstrate the framework’s ability to identify high-damage spatial areas that would be overlooked by baseline models. the satisfactory performance of FloodDamageCast also shows its capability to be used for flood damage nowcasting at a fine spatial resolution to inform response and recovery efforts. The insights from flood damage nowcasting would help emergency management agencies and public officials to more efficiently identify repair needs and allocate resources, and also save time and efforts during on-the-ground inspections.

在应对和恢复工作中，对建筑物和基础设施的损失进行近实时估算（又称损失预报）至关重要。尽管在洪水风险预测方面取得了进步，但现有的大多数方法主要侧重于淹没估计，而损害预报能力有限。精细空间分辨率下的洪水灾害预报仍然是一个极具挑战性的问题，目前还没有任何现有模型可以完成这项任务。造成这一局限性的主要原因是一系列技术挑战，如对洪水灾害与建筑环境特征之间的非线性相互作用考虑有限、数据集不平衡问题以及缺乏可靠的地面实况来评估模型性能。为了解决这一重要问题，本研究提出了 FloodDamageCast，这是一个专为财产洪灾损失预报量身定制的机器学习（ML）框架。该框架利用与建筑环境、地形和水文特征相关的异构数据，以德克萨斯州哈里斯县为背景，以 500 米乘 500 米的精细分辨率预测 2017 年 "哈维 "飓风期间的住宅洪灾损失。为解决数据不平衡问题，FloodDamageCast 包含一个基于条件表生成对抗网络 (CTGAN) 的表格式数据增强模型。通过将基于 GAN 的数据增强与高效 ML 模型 Light Gradient-Boosting Machine (LightGBM) 相结合，我们的结果表明该框架有能力识别基线模型会忽略的高损害空间区域。FloodDamageCast 的令人满意的性能还表明它有能力用于精细空间分辨率的洪水损害预报，为响应和恢复工作提供信息。洪水灾害预报的洞察力将帮助应急管理机构和政府官员更有效地确定修复需求和分配资源，并节省实地检查的时间和精力。

{"title":"FloodDamageCast: Building flood damage nowcasting with machine-learning and data augmentation","authors":"Chia-Fu Liu , Lipai Huang , Kai Yin , Sam Brody , Ali Mostafavi","doi":"10.1016/j.ijdrr.2024.104971","DOIUrl":"10.1016/j.ijdrr.2024.104971","url":null,"abstract":"<div><div>Near-real-time estimation of damages (a.k.a, damage nowcasting) to building and infrastructure is crucial during response and recovery efforts. Despite advancements in flood risk predictions, the majority of existing methods primarily focus on inundation estimation with limited damage nowcasting capabilities. Flooding damage nowcasting at fine spatial resolutions remains a very challenging problem with currently no existing model to perform the task. This limitation is mainly due to a number of technical challenges such as limited consideration of non-linear interactions between flood hazards and build-environment features, issues with imbalanced datasets, and the absence of reliable ground truth for model performance evaluation. To address this important gap, this study presents FloodDamageCast, a machine learning (ML) framework tailored for property flood damage nowcasting. The framework leverages heterogeneous data related to the built environment, topographic, and hydrological features to predict residential flood damage in a fine resolution of 500 m by 500 m in the context of Harris County, TX, during the 2017 Hurricane Harvey. To deal with data imbalance, FloodDamageCast includes a tabular data augmentation model based on Conditional Tabular Generative Adversarial Networks (CTGAN). The data augmentation model component addresses highly imbalanced class issues, where the majority class constitutes 96.4% of the dataset, potentially impairing model performance, By combining GAN-based data augmentation with an efficient ML model, Light Gradient-Boosting Machine (LightGBM), our results demonstrate the framework’s ability to identify high-damage spatial areas that would be overlooked by baseline models. the satisfactory performance of FloodDamageCast also shows its capability to be used for flood damage nowcasting at a fine spatial resolution to inform response and recovery efforts. The insights from flood damage nowcasting would help emergency management agencies and public officials to more efficiently identify repair needs and allocate resources, and also save time and efforts during on-the-ground inspections.</div></div>","PeriodicalId":13915,"journal":{"name":"International journal of disaster risk reduction","volume":"114 ","pages":"Article 104971"},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0